MIT Libraries homeMIT Libraries logoDSpace@MIT

MIT
Search 
  • DSpace@MIT Home
  • Center for Brains, Minds & Machines
  • Publications
  • CBMM Memo Series
  • Search
  • DSpace@MIT Home
  • Center for Brains, Minds & Machines
  • Publications
  • CBMM Memo Series
  • Search
JavaScript is disabled for your browser. Some features of this site may not work without it.

Search

Show Advanced FiltersHide Advanced Filters

Filters

Use filters to refine the search results.

Now showing items 1-10 of 18

  • Sort Options:
  • Relevance
  • Title Asc
  • Title Desc
  • Issue Date Asc
  • Issue Date Desc
  • Results Per Page:
  • 5
  • 10
  • 20
  • 40
  • 60
  • 80
  • 100
Thumbnail

Unsupervised learning of clutter-resistant visual representations from natural videos 

Liao, Qianli; Leibo, Joel Z; Poggio, Tomaso (Center for Brains, Minds and Machines (CBMM), arXiv, 2015-04-27)
Populations of neurons in inferotemporal cortex (IT) maintain an explicit code for object identity that also tolerates transformations of object appearance e.g., position, scale, viewing angle [1, 2, 3]. Though the learning ...
Thumbnail

The Invariance Hypothesis Implies Domain-Specific Regions in Visual Cortex 

Leibo, Joel Z; Liao, Qianli; Anselmi, Fabio; Poggio, Tomaso (Center for Brains, Minds and Machines (CBMM), bioRxiv, 2015-04-26)
Is visual cortex made up of general-purpose information processing machinery, or does it consist of a collection of specialized modules? If prior knowledge, acquired from learning a set of objects is only transferable to ...
Thumbnail

Learning Real and Boolean Functions: When Is Deep Better Than Shallow 

Mhaskar, Hrushikesh; Liao, Qianli; Poggio, Tomaso (Center for Brains, Minds and Machines (CBMM), arXiv, 2016-03-08)
We describe computational tasks - especially in vision - that correspond to compositional/hierarchical functions. While the universal approximation property holds both for hierarchical and shallow networks, we prove that ...
Thumbnail

Theory I: Why and When Can Deep Networks Avoid the Curse of Dimensionality? 

Poggio, Tomaso; Mhaskar, Hrushikesh; Rosasco, Lorenzo; Miranda, Brando; Liao, Qianli (Center for Brains, Minds and Machines (CBMM), arXiv, 2016-11-23)
[formerly titled "Why and When Can Deep – but Not Shallow – Networks Avoid the Curse of Dimensionality: a Review"] The paper reviews and extends an emerging body of theoretical results on deep learning including the ...
Thumbnail

Bridging the Gaps Between Residual Learning, Recurrent Neural Networks and Visual Cortex 

Liao, Qianli; Poggio, Tomaso (Center for Brains, Minds and Machines (CBMM), arXiv, 2016-04-12)
We discuss relations between Residual Networks (ResNet), Recurrent Neural Networks (RNNs) and the primate visual cortex. We begin with the observation that a shallow RNN is exactly equivalent to a very deep ResNet with ...
Thumbnail

View-tolerant face recognition and Hebbian learning imply mirror-symmetric neural tuning to head orientation 

Leibo, Joel Z.; Liao, Qianli; Freiwald, Winrich; Anselmi, Fabio; Poggio, Tomaso (Center for Brains, Minds and Machines (CBMM), arXiv, 2016-06-03)
The primate brain contains a hierarchy of visual areas, dubbed the ventral stream, which rapidly computes object representations that are both specific for object identity and relatively robust against identity-preserving ...
Thumbnail

Streaming Normalization: Towards Simpler and More Biologically-plausible Normalizations for Online and Recurrent Learning 

Liao, Qianli; Kawaguchi, Kenji; Poggio, Tomaso (Center for Brains, Minds and Machines (CBMM), arXiv, 2016-10-19)
We systematically explored a spectrum of normalization algorithms related to Batch Normalization (BN) and propose a generalized formulation that simultaneously solves two major limitations of BN: (1) online learning and ...
Thumbnail

Musings on Deep Learning: Properties of SGD 

Zhang, Chiyuan; Liao, Qianli; Rakhlin, Alexander; Sridharan, Karthik; Miranda, Brando; e.a. (Center for Brains, Minds and Machines (CBMM), 2017-04-04)
[previously titled "Theory of Deep Learning III: Generalization Properties of SGD"] In Theory III we characterize with a mix of theory and experiments the generalization properties of Stochastic Gradient Descent in ...
Thumbnail

3D Object-Oriented Learning: An End-to-end Transformation-Disentangled 3D Representation 

Liao, Qianli; Poggio, Tomaso (2017-12-31)
We provide more detailed explanation of the ideas behind a recent paper on “Object-Oriented Deep Learning” [1] and extend it to handle 3D inputs/outputs. Similar to [1], every layer of the system takes in a list of ...
Thumbnail

Theory II: Landscape of the Empirical Risk in Deep Learning 

Poggio, Tomaso; Liao, Qianli (Center for Brains, Minds and Machines (CBMM), arXiv, 2017-03-30)
Previous theoretical work on deep learning and neural network optimization tend to focus on avoiding saddle points and local minima. However, the practical observation is that, at least for the most successful Deep ...
  • 1
  • 2

Browse

All of DSpaceCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

My Account

Login

Discover

Author
Liao, Qianli (18)
Poggio, Tomaso (18)Miranda, Brando (6)Hidary, Jack (3)Mhaskar, Hrushikesh (3)Anselmi, Fabio (2)Kawaguchi, Kenji (2)Leibo, Joel Z (2)Leibo, Joel Z. (2)Rakhlin, Alexander (2)... View MoreSubjectComputer vision (4)Batch Normalization (BN) (2)Machine Learning (2)primate visual cortex (2)AI (1)Artificial Intelligence (1)artificial intelligence (1)backpropagation (1)CIFAR-10 (1)computational tasks (1)... View MoreDate Issued2017 (7)2016 (5)2015 (3)2018 (3)Has File(s)Yes (18)

Statistics

OA StatisticsStatistics by CountryStatistics by Department
MIT Libraries homeMIT Libraries logo

Find us on

Twitter Facebook Instagram YouTube RSS

MIT Libraries navigation

SearchHours & locationsBorrow & requestResearch supportAbout us
PrivacyPermissionsAccessibility
MIT
Massachusetts Institute of Technology
Content created by the MIT Libraries, CC BY-NC unless otherwise noted. Notify us about copyright concerns.